• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.12
• /
• pp.471-480
• /
• 2016

Recently, the damage of cyber attack toward infra-system, national defence and security system is gradually increasing. In this situation, military recognizes the importance of cyber warfare, and they establish a cyber system in preparation, regardless of the existence of threaten. Thus, the study of Intrusion Detection System(IDS) that plays an important role in network defence system is required. IDS is divided into misuse and anomaly detection methods. Recent studies attempt to combine those two methods to maximize advantagesand to minimize disadvantages both of misuse and anomaly. The combination is called Hybrid IDS. Previous studies would not be inappropriate for near real-time network environments because they have computational complexity problems. It leads to the need of the study considering the structure of IDS that have high detection rate and low computational cost. In this paper, we proposed a Hybrid IDS which combines C4.5 decision tree(misuse detection method) and Weighted K-means algorithm (anomaly detection method) hierarchically. It can detect malicious network packets effectively with low complexity by applying mutual information and genetic algorithm based efficient feature selection technique. Also we construct upgraded the the hierarchical structure of IDS reusing feature weights in anomaly detection section. It is validated that proposed Hybrid IDS ensures high detection accuracy (98.68%) and performance at experiment section.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.491-501
• /
• 2019

In side-channel analysis, which exploit physical leakage from a cryptographic device, deep learning based attack has been significantly interested in recent years. However, most of the state-of-the-art methods have been focused on classifying side-channel information in a profiled scenario where attackers can obtain label of training data. In this paper, we propose a new method based on deep learning to improve non-profiling side-channel attack such as Differential Power Analysis and Correlation Power Analysis. The proposed method is a signal preprocessing technique that reduces the noise in a trace by modifying Auto-Encoder framework to the context of side-channel analysis. Previous work on Denoising Auto-Encoder was trained through randomly added noise by an attacker. In this paper, the proposed model trains Auto-Encoder through the noise from real data using the noise-reduced-label. Also, the proposed method permits to perform non-profiled attack by training only a single neural network. We validate the performance of the noise reduction of the proposed method on real traces collected from ChipWhisperer board. We demonstrate that the proposed method outperforms classic preprocessing methods such as Principal Component Analysis and Linear Discriminant Analysis.

• Journal of IKEEE
• /
• v.23 no.2
• /
• pp.438-447
• /
• 2019

As the IoT-based hyper-connected society grows, public-key cryptosystem such as RSA is frequently used for encryption, authentication, and digital signature. Public-key cryptosystem use very large (safe) prime numbers to ensure security against malicious attacks. Even though the performance of the device has greatly improved, the generation of a large (safe)prime is time-consuming or memory-intensive. In this paper, we propose ET-MR and ET-MR-MR using Euler sieve so it runs faster while using less memory. We present a running time prediction model by probabilistic analysis and compare time and memory of our method with conventional methods. Experimental results show that the difference between the expected running time and the measured running time is less than 4%. In addition, the fastest running time of ET-MR is 36% faster than that of TD-MR, 8.5% faster than that of DT-MR and the fastest running time of ET-MR-MR is 65.3% faster than that of TD-MR-MR and similar to that of DT-MR-MR. When k=12,381, the memory usage of ET-MR is 2.7 times more than that of DT-MR but 98.5% less than that of TD-MR and when k=65,536, the memory usage of ET-MR-MR is 98.48% less than that of TD-MR-MR and 92.8% less than that of DT-MR-MR.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.1
• /
• pp.43-56
• /
• 2012

Wireless sensor networks consist of numerous small-sized nodes equipped with limited computing power and storage as well as energy-limited disposable batteries. In this networks, nodes are deployed in a large given area and communicate with each other in short distances via wireless links. For energy efficient networks, dynamic clustering protocol is an effective technique to achieve prolonged network lifetime, scalability, and load balancing which are known as important requirements. this technique has a characteristic that sensing data which gathered by many nodes are aggregated by cluster head node. In the case of cluster head node is exposed by attacker, there is no guarantee of safe and stable network. Therefore, for secure communications in such a sensor network, it is important to be able to encrypt the messages transmitted by sensor nodes. Especially, cluster based sensor networks that are designed for energy efficient, strongly recommended suitable key management and authentication methods to guarantee optimal stability. To achieve secured network, we propose a key management scheme which is appropriate for hierarchical sensor networks. Proposed scheme is based on polynomial key pool pre-distribution scheme, and sustain a stable network through key authentication process.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1115-1130
• /
• 2020

Modern vehicles are equipped with a number of ECUs(Electronic Control Units), and ECUs can control vehicles efficiently by communicating each other through CAN(Controller Area Network). However, CAN bus is known to be vulnerable to cyber attacks because of the lack of message authentication and message encryption, and access control. To find these security issues related to vehicle hacking, CAN Fuzzing methods, that analyze the vulnerabilities of ECUs, have been studied. In the existing CAN Fuzzing methods, fuzzing inputs are randomly generated without considering the structure of CAN messages transmitted by ECUs, which results in the non-negligible fuzzing time. In addition, the existing fuzzing solutions have limitations in how to monitor fuzzing results. To deal with the limitations of CAN Fuzzing, in this paper, we propose a Non-Random CAN Fuzzing, which consider the structure of CAN messages and systematically generates fuzzing input values that can cause malfunctions to ECUs. The proposed Non-Random CAN Fuzzing takes less time than the existing CAN Fuzzing solutions, so it can quickly find CAN messages related to malfunctions of ECUs that could be originated from SW implementation errors or CAN DBC(Database CAN) design errors. We evaluated the performance of Non-Random CAN Fuzzing by conducting an experiment in a real vehicle, and proved that the proposed method can find CAN messages related to malfunctions faster than the existing fuzzing solutions.

• Journal of Software Assessment and Valuation
• /
• v.16 no.1
• /
• pp.65-79
• /
• 2020

As Programmable Logic Controllers (PLCs), popular components in industrial control systems (ICS), are incorporated with the technologies such as micro-controllers, real-time operating systems, and communication capabilities. As the latest PLCs have been connected to the Internet, they are becoming a main target of cyber threats. This paper proposes two sanitizers that improve the security of uC/OS-II based firmware for a PLC. That is, we devise BU sanitizer for detecting out-of-bounds accesses to buffers and UaF sanitizer for fixing use-after-free bugs in the firmware. They can sanitize the binary firmware image generated in a desktop PC before downloading it to the PLC. The BU sanitizer can also detect the violation of control flow integrity using both call graph and symbols of functions in the firmware image. We have implemented the proposed two sanitizers as a prototype system on a PLC running uC/OS-II and demonstrated the effectiveness of them by performing experiments as well as comparing them with the existing sanitizers. These findings can be used to detect and mitigate unintended vulnerabilities during the firmware development phase.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.1019-1034
• /
• 2022

Malware attacks become more prevalent in the hyper-connected society of the 4th industrial revolution. To respond to such malware, automation of malware detection using artificial intelligence technology is attracting attention as a new alternative. However, using artificial intelligence without collateral for its reliability poses greater risks and side effects. The EU and the United States are seeking ways to secure the reliability of artificial intelligence, and the government announced a reliable strategy for realizing artificial intelligence in 2021. The government's AI reliability has five attributes: Safety, Explainability, Transparency, Robustness and Fairness. We develop four elements of safety, explainable, transparent, and fairness, excluding robustness in the malware detection model. In particular, we demonstrated stable generalization performance, which is model accuracy, through the verification of external agencies, and developed focusing on explainability including transparency. The artificial intelligence model, of which learning is determined by changing data, requires life cycle management. As a result, demand for the MLops framework is increasing, which integrates data, model development, and service operations. EXE-executable malware and documented malware response services become data collector as well as service operation at the same time, and connect with data pipelines which obtain information for labeling and purification through external APIs. We have facilitated other security service associations or infrastructure scaling using cloud SaaS and standard APIs.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.67-76
• /
• 2023

Although deep learning models are making innovative achievements in the field of computer vision, the problem of vulnerability to adversarial examples continues to be raised. Adversarial examples are attack methods that inject fine noise into images to induce misclassification, which can pose a serious threat to the application of deep learning models in the real world. In this paper, we propose a model that detects adversarial examples using differences in predictive values between edge-learned classification models and underlying classification models. The simple process of extracting the edges of the objects and reflecting them in learning can increase the robustness of the classification model, and economical and efficient detection is possible by detecting adversarial examples through differences in predictions between models. In our experiments, the general model showed accuracy of {49.9%, 29.84%, 18.46%, 4.95%, 3.36%} for adversarial examples (eps={0.02, 0.05, 0.1, 0.2, 0.3}), whereas the Canny edge model showed accuracy of {82.58%, 65.96%, 46.71%, 24.94%, 13.41%} and other edge models showed a similar level of accuracy also, indicating that the edge model was more robust against adversarial examples. In addition, adversarial example detection using differences in predictions between models revealed detection rates of {85.47%, 84.64%, 91.44%, 95.47%, and 87.61%} for each epsilon-specific adversarial example. It is expected that this study will contribute to improving the reliability of deep learning models in related research and application industries such as medical, autonomous driving, security, and national defense.